Quantitative assessment of machine-learning segmentation of battery electrode materials for active material quantification

X-ray computed tomography (CT) is an important tool for studying battery electrode microstructures but relies on robust segmentation for validity. Here, several approaches to applying accessible machine-learning segmentation software to segment open-source lithium-ion battery (LIB) electrode tomograms are followed to identify the optimised methodology that minimises variation in active material volume fraction quantification across three users. Iterative, manual training across seven cross-sectional slices (<5%) of a tomogram is identified as an optimal balance between variance and user interaction, where 10–25% of each slice was trained. This approach is applied to lab-based X-ray CT data and compared with data obtained by focused-ion beam/scanning electron microscopy slice-and-view tomography. Variation in active material volume fraction between users is lower for at least one of these two approaches (10% or 25%) when applied to raw LIB cathode tomograms, versus unsupervised techniques such as simple and watershed segmentations. On average, the absolute volume fraction values are closer to that acquired by the correlated technique, most closely matching for high-resolution data. The present analysis provides an optimised approach for using open-source software to apply machine-learning segmentation when quantifying active material volume fractions in cutting-edge LIB electrodes, providing a more robust route to active material quantification.